Multiscale Hessian filtering for enhancement of OCT angiography images

Ratheesh K. Meleppat, Eric B. Miller, Suman K. Manna, Pengfei Zhang, Edward N Pugh Jr, Robert Zawadzki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The comprehensive architectural analysis of the retinal vasculature would greatly aid with the diagnosis and management of many ocular diseases. Optical coherence tomography angiography (OCTA) is a powerful micrometerlevel resolution, high sensitivity, and potentially large field of view retinal imaging modality that allows assessment of 2D and 3D microvascular networks. However, the quality of retinal OCTA images are often degraded by the noise and poor vascular contrast. Digital image filters are widely used in medical diagnostic to selectively enhance specific local intensity profiles or structures such as vasculatures. Most successful feature enhancement filters employ Hessian matrix and eigen values-based approach. In this paper, we demonstrate the feasibility of multiscale Hessian filters for the enhancement of the OCTA images of a mouse retina. We show that the enhancement filter based on the ratio of Hessian eigenvalues proposed by Jerman et al. (Jerman filter) performs better than the most commonly used Frangi's method. This improved performance included close-to-uniform response in all vascular structures and enhancement of visibility of vascular structures with non-circular cross-sections. To evaluate and compare performance, different multi-scale Hessian filtering was performed on OCTA images of different inner retina vascular beds of a mouse eye.

Original languageEnglish (US)
Title of host publicationOphthalmic Technologies XXIX
EditorsPer G. Soderberg, Fabrice Manns, Arthur Ho
PublisherSPIE
ISBN (Electronic)9781510623583
DOIs
StatePublished - Jan 1 2019
Event29th Conference on Ophthalmic Technologies - San Francisco, United States
Duration: Feb 2 2019Feb 3 2019

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10858
ISSN (Print)1605-7422

Conference

Conference29th Conference on Ophthalmic Technologies
CountryUnited States
CitySan Francisco
Period2/2/192/3/19

Fingerprint

Angiography
angiography
Optical tomography
Optical Coherence Tomography
Blood Vessels
tomography
filters
augmentation
retina
mice
Retina
image filters
Hessian matrices
Eye Diseases
Microvessels
visibility
Visibility
field of view
Noise
beds

Keywords

  • Angiography
  • Hessian filtering
  • Image enhancement
  • Optical coherence tomography

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Meleppat, R. K., Miller, E. B., Manna, S. K., Zhang, P., Pugh Jr, E. N., & Zawadzki, R. (2019). Multiscale Hessian filtering for enhancement of OCT angiography images. In P. G. Soderberg, F. Manns, & A. Ho (Eds.), Ophthalmic Technologies XXIX [108581K] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10858). SPIE. https://doi.org/10.1117/12.2511044

Multiscale Hessian filtering for enhancement of OCT angiography images. / Meleppat, Ratheesh K.; Miller, Eric B.; Manna, Suman K.; Zhang, Pengfei; Pugh Jr, Edward N; Zawadzki, Robert.

Ophthalmic Technologies XXIX. ed. / Per G. Soderberg; Fabrice Manns; Arthur Ho. SPIE, 2019. 108581K (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10858).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meleppat, RK, Miller, EB, Manna, SK, Zhang, P, Pugh Jr, EN & Zawadzki, R 2019, Multiscale Hessian filtering for enhancement of OCT angiography images. in PG Soderberg, F Manns & A Ho (eds), Ophthalmic Technologies XXIX., 108581K, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10858, SPIE, 29th Conference on Ophthalmic Technologies, San Francisco, United States, 2/2/19. https://doi.org/10.1117/12.2511044
Meleppat RK, Miller EB, Manna SK, Zhang P, Pugh Jr EN, Zawadzki R. Multiscale Hessian filtering for enhancement of OCT angiography images. In Soderberg PG, Manns F, Ho A, editors, Ophthalmic Technologies XXIX. SPIE. 2019. 108581K. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2511044
Meleppat, Ratheesh K. ; Miller, Eric B. ; Manna, Suman K. ; Zhang, Pengfei ; Pugh Jr, Edward N ; Zawadzki, Robert. / Multiscale Hessian filtering for enhancement of OCT angiography images. Ophthalmic Technologies XXIX. editor / Per G. Soderberg ; Fabrice Manns ; Arthur Ho. SPIE, 2019. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{f28ddfc1f6494718b06834cc7c0e74d9,
title = "Multiscale Hessian filtering for enhancement of OCT angiography images",
abstract = "The comprehensive architectural analysis of the retinal vasculature would greatly aid with the diagnosis and management of many ocular diseases. Optical coherence tomography angiography (OCTA) is a powerful micrometerlevel resolution, high sensitivity, and potentially large field of view retinal imaging modality that allows assessment of 2D and 3D microvascular networks. However, the quality of retinal OCTA images are often degraded by the noise and poor vascular contrast. Digital image filters are widely used in medical diagnostic to selectively enhance specific local intensity profiles or structures such as vasculatures. Most successful feature enhancement filters employ Hessian matrix and eigen values-based approach. In this paper, we demonstrate the feasibility of multiscale Hessian filters for the enhancement of the OCTA images of a mouse retina. We show that the enhancement filter based on the ratio of Hessian eigenvalues proposed by Jerman et al. (Jerman filter) performs better than the most commonly used Frangi's method. This improved performance included close-to-uniform response in all vascular structures and enhancement of visibility of vascular structures with non-circular cross-sections. To evaluate and compare performance, different multi-scale Hessian filtering was performed on OCTA images of different inner retina vascular beds of a mouse eye.",
keywords = "Angiography, Hessian filtering, Image enhancement, Optical coherence tomography",
author = "Meleppat, {Ratheesh K.} and Miller, {Eric B.} and Manna, {Suman K.} and Pengfei Zhang and {Pugh Jr}, {Edward N} and Robert Zawadzki",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2511044",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Soderberg, {Per G.} and Fabrice Manns and Arthur Ho",
booktitle = "Ophthalmic Technologies XXIX",

}

TY - GEN

T1 - Multiscale Hessian filtering for enhancement of OCT angiography images

AU - Meleppat, Ratheesh K.

AU - Miller, Eric B.

AU - Manna, Suman K.

AU - Zhang, Pengfei

AU - Pugh Jr, Edward N

AU - Zawadzki, Robert

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The comprehensive architectural analysis of the retinal vasculature would greatly aid with the diagnosis and management of many ocular diseases. Optical coherence tomography angiography (OCTA) is a powerful micrometerlevel resolution, high sensitivity, and potentially large field of view retinal imaging modality that allows assessment of 2D and 3D microvascular networks. However, the quality of retinal OCTA images are often degraded by the noise and poor vascular contrast. Digital image filters are widely used in medical diagnostic to selectively enhance specific local intensity profiles or structures such as vasculatures. Most successful feature enhancement filters employ Hessian matrix and eigen values-based approach. In this paper, we demonstrate the feasibility of multiscale Hessian filters for the enhancement of the OCTA images of a mouse retina. We show that the enhancement filter based on the ratio of Hessian eigenvalues proposed by Jerman et al. (Jerman filter) performs better than the most commonly used Frangi's method. This improved performance included close-to-uniform response in all vascular structures and enhancement of visibility of vascular structures with non-circular cross-sections. To evaluate and compare performance, different multi-scale Hessian filtering was performed on OCTA images of different inner retina vascular beds of a mouse eye.

AB - The comprehensive architectural analysis of the retinal vasculature would greatly aid with the diagnosis and management of many ocular diseases. Optical coherence tomography angiography (OCTA) is a powerful micrometerlevel resolution, high sensitivity, and potentially large field of view retinal imaging modality that allows assessment of 2D and 3D microvascular networks. However, the quality of retinal OCTA images are often degraded by the noise and poor vascular contrast. Digital image filters are widely used in medical diagnostic to selectively enhance specific local intensity profiles or structures such as vasculatures. Most successful feature enhancement filters employ Hessian matrix and eigen values-based approach. In this paper, we demonstrate the feasibility of multiscale Hessian filters for the enhancement of the OCTA images of a mouse retina. We show that the enhancement filter based on the ratio of Hessian eigenvalues proposed by Jerman et al. (Jerman filter) performs better than the most commonly used Frangi's method. This improved performance included close-to-uniform response in all vascular structures and enhancement of visibility of vascular structures with non-circular cross-sections. To evaluate and compare performance, different multi-scale Hessian filtering was performed on OCTA images of different inner retina vascular beds of a mouse eye.

KW - Angiography

KW - Hessian filtering

KW - Image enhancement

KW - Optical coherence tomography

UR - http://www.scopus.com/inward/record.url?scp=85067693380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067693380&partnerID=8YFLogxK

U2 - 10.1117/12.2511044

DO - 10.1117/12.2511044

M3 - Conference contribution

AN - SCOPUS:85067693380

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Ophthalmic Technologies XXIX

A2 - Soderberg, Per G.

A2 - Manns, Fabrice

A2 - Ho, Arthur

PB - SPIE

ER -